Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Neural network”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,207 records · Page 67Linked to original sources
PubMed1998

A neural network classifier with disjunctive fuzzy information.

This paper presents a neural network classifier that learns disjunctive fuzzy information in the feature space. This neural network consists of two types of nodes in the hidden layer. The prototype nodes and exemplar nodes represent cluster centroids and exceptions in the feature space, respectively. This classifier automatically generates and refines prototypes for distinct clusters in the feature space. The number and sizes of these prototypes are not restricted, so the prototypes will form near-optimal decision regions to meet the distribution of input patterns and classify as many input patterns as possible. Next, exemplars will be created and expanded to learn the patterns that cannot be classified by the prototypes. Such a training strategy can reduce the memory requirement and speed up the process of non-linear classification. In addition, on-line learning is supplied in this classifier and the computational load is lightened. The experimental results manifest that this model can reduce the number of hidden nodes by determining the appropriate number of prototype nodes.

Journal Article↗
PubMed2005

Full-state tracking control of a mobile robot using neural networks.

In this paper a nonholonomic mobile robot with completely unknown dynamics is discussed. A mathematical model has been considered and an efficient neural network is developed, which ensures guaranteed tracking performance leading to stability of the system. The neural network assumes a single layer structure, by taking advantage of the robot regressor dynamics that expresses the highly nonlinear robot dynamics in a linear form in terms of the known and unknown robot dynamic parameters. No assumptions relating to the boundedness is placed on the unmodeled disturbances. It is capable of generating real-time smooth and continuous velocity control signals that drive the mobile robot to follow the desired trajectories. The proposed approach resolves speed jump problem existing in some previous tracking controllers. Further, this neural network does not require offline training procedures. Lyapunov theory has been used to prove system stability. The practicality and effectiveness of the proposed tracking controller are demonstrated by simulation and comparison results.

Artificial Intelligence↗
PubMed2006

Artificial neural network based identification of Campylobacter species by Fourier transform infrared spectroscopy.

Two prototypes of artificial neural network (ANN), multilayer perceptron (MLP), and probabilistic neural network (PNN), were used to analyze infrared (IR) spectral data obtained from intact cells belonging to the species Campylobacter coli and Campylobacter jejuni. In order to establish a consistent identification and typing procedure, mid infrared spectra of these species were obtained by means of a Fourier transform infrared (FT-IR) spectroscope. FT-IR patterns belonging to 26 isolates subclassified into 4 genotypes were pre-processed (normalized, smoothed and derivatized) and grouped into training, verification and test sets. The two architectures tested (PNN, MLP) were developed and trained to identify or leave unassigned a number of IR patterns. Two window ranges (w(4), 1200 to 900 cm(-1); and w(5), 900 to 700 cm(-1)) in the mid IR spectrum were presented as input to the ANN models functioning as pattern recognition systems. No matter the ANN used all the training sets were correctly identified at subspecies level. For the test set, the four-layer MLP network was found to be specially suitable to recognize FT-IR data since it correctly identified 99.16% of unknowns using the w(4) range, and was fully successful in detecting atypical patterns from closely related Campylobacter strains and other bacterial species. The PNN network obtained lower percentages in assignation and rejection. Overall, ANNs constitute an excellent mathematical tool in microbial identification, since they are able to recognize with a high degree of confidence typical as well as atypical FT-IR fingerprints from Campylobacter spp.

Campylobacter↗
PubMed1996

Fuel identification by neural network analysis of the response of vapor-sensitive sensor arrays.

Neural network analysis of the response of an array of vapor-sensitive detectors has been used to identify six different types of aviation fuel. The data set included 96 samples of JP-4, JP-5, JP-7, JP-8, JetA, and aviation gasoline (AvGas). A sample of each neat fuel was injected into a continuous stream of breathing air through an injection port from a gas chromatograph. The aspirated sample was then swept from the injection port to the chamber without separation. In the chamber, the sample was exposed to an array of eight vapor-sensitive detectors. The analog output of each detector was digitized and stored while the sample was swept into and through the chamber. The response of each detector was then averaged and stored as the final response or pattern of each sample. It was clear from a visual inspection of each of the radar plots that there was a characteristic pattern in the response of the array to five of the six different fuel types. This was confirmed using neural network analysis to study the entire data set. A two-step procedure was developed to separate the patterns of all six fuel tyes into their respective classes. In the first step, fuels were separated into one of five groups: JP-4, JP-5, JP-7, AvGas, or a combined JP-8/JetA group. In the second step, the fuels in the combined group were separated into either JP-8 or JetA groups.

Chromatography, Gas↗
PubMed1997

Long-term identification of streptomycetes using pyrolysis mass spectrometry and artificial neural networks.

Sixteen reference strains and thirteen fresh isolates of three putatively novel Streptomyces species were examined six times over twenty months using pyrolysis mass spectrometry to examine the long-term reproducibility of the procedure. The reference strains and new isolates were correctly identified using information in each of the datasets and operational fingerprinting, but direct statistical comparison of the datasets for strain identification was unsuccessful between datasets. Artificial neural networks were also used to identify the strains held in the datasets. Neural networks trained with pyrolysis mass spectra from a single dataset were found to successfully identify the reference strains and fresh isolates in that dataset but were unable to identify many of the strains in the other datasets. However, a neural network trained on representative pyrolysis mass spectra from each of the first three datasets were found to identify the reference strains and fresh isolates in those three datasets and in the three subsequent datasets. Therefore, artificial neural network analysis of pyrolysis mass spectrometric data can provide a rapid, cost-effective, accurate and long-term reproducible way of identifying and typing microorganisms.

Humans↗
PubMed2000

Neural network schemes for detecting rare events in human genomic DNA.

MOTIVATION: Many problems in molecular biology as well as other areas involve detection of rare events in unbalanced data. We develop two sample stratification schemes in conjunction with neural networks for rare event detection in such databases. Sample stratification is a technique for making each class in a sample have equal influence on decision making. The first scheme proposed stratifies a sample by adding up the weighted sum of the derivatives during the backward pass of training. The second scheme proposed uses a technique of modified bootstrap aggregating. After training neural networks with multiple sets of bootstrapped examples of the rare event classes and subsampled examples of common event classes, multiple voting for classification is performed. RESULTS: These two schemes make rare event classes have a better chance of being included in the sample used for training neural networks and thus improve the classification accuracy for rare event detection. The experimental performance of the two schemes using two sets of human DNA sequences as well as another set of Gaussian data indicates that proposed schemes have the potential of significantly improving accuracy of neural networks to recognize rare events.

Algorithms↗
PubMed2000

Neural network application in the discrimination of benign from malignant gastric cells.

OBJECTIVE: To investigate the potential value of morphometry and neural networks for the discrimination of benign from malignant gastric lesions. STUDY DESIGN: One thousand cells from 19 cases of cancer, 19 cases of gastritis and 56 cases of ulcer were selected as a training set, and an additional 4,000 cells from the same cases of cancer, gastritis and ulcer were used as a test set. Images of routinely processed gastric smears stained by the Papanicolaou technique were analyzed by a custom-made image analysis system. RESULTS: Application of the neural network gave correct classification in 96% of benign cells and 89% of malignant cells. CONCLUSION: The results indicate that the use of neural networks and image morphometry may offer useful information concerning the potential of malignancy in gastric cells.

Cytodiagnosis↗
PubMed2005

Prediction of vascular tissue engineering results with artificial neural networks.

Tissue engineers are often confused on finding the most successful strategy for specific patient. In this study, we used artificial neural networks to predict the outcomes of different vascular tissue engineering strategies, thus providing advisory information for experimental designers. Over 30 variables were used as features of the tissue engineering strategies. Different architectures of artificial neural networks with back propagation algorithm were tested to obtain the best model configuration for the prediction of the tissue engineering strategies. In the computational experiments, the artificial neural networks with one and two hidden layers could, respectively, detect unsuccessful strategies with the highest predictive accuracy of 91.45 and 94.24%. In conclusion, artificial intelligence has great potential in tissue engineering decision support. It can provide accurate advisory information for tissue engineers, thus reducing failures and improving therapeutic effects.

Animals↗
PubMed2004

Congestion control for ATM multiplexers using neural networks: multiple sources/single buffer scenario.

A new neural network based method for solving the problem of congestion control arising at the user network interface (UNI) of ATM networks is proposed in this paper. Unlike the previous methods where the coding rate for all traffic sources as controller output signals is tuned in a body, the proposed method adjusts the coding rate for only a part of the traffic sources while the remainder sources send the cells in the previous coding rate in case of occurrence of congestion. The controller output signals include the source coding rate and the percentage of the sources that send cells at the corresponding coding rate. The control methods not only minimize the cell loss rate but also guarantee the quality of information (such as voice sources) fed into the multiplexer buffer. Simulations with 150 ADPCM voice sources fed into the multiplexer buffer showed that the proposed methods have advantage over the previous methods in the aspect of the performance indices such as cell loss rate (CLR) and voice quality.

Algorithms↗
PubMed2006

Dynamic and interactive generation of object handling behaviors by a small humanoid robot using a dynamic neural network model.

This study presents experiments on the learning of object handling behaviors by a small humanoid robot using a dynamic neural network model, the recurrent neural network with parametric bias (RNNPB). The first experiment showed that after the robot learned different types of ball handling behaviors using human direct teaching, the robot was able to generate adequate ball handling motor sequences situated to the relative position between the robot's hands and the ball. The same scheme was applied to a block handling learning task where it was shown that the robot can switch among learned different block handling sequences, situated to the ways of interaction by human supporters. Our analysis showed that entrainment of the internal memory structures of the RNNPB through the interactions of the objects and the human supporters are the essential mechanisms for those observed situated behaviors of the robot.

Algorithms↗
PubMed1996

Correction of mass spectral drift using artificial neural networks.

For pyrolysis mass spectrometry (PyMS) to be used for the routine identification of microorganisms, for quantifying determinands in biological and biotechnological systems, and in the production of useful mass spectral libraries, it is paramount that newly acquired spectra be compared to those previously collected. Neural network and other multivariate calibration models have been used to relate mass spectra to the biological features of interest. As commonly observed, however, mass spectral fingerprints showed a lack of long-term reproducibility, due to instrumental drift in the mass spectrometer; when identical materials were analyzed by PyMS at dates from 4 to 20 months apart, neural network models produced at earlier times could not be used to give accurate estimates of determinand concentrations or bacterial identities. Neural networks, however, can be used to correct for pyrolysis mass spectrometer instrumental drift itself, so that neural network or other multivariate calibration models created using previously collected data can be used to give accurate estimates of determinand concentration or the nature of bacteria (or, indeed, other materials) from newly acquired pyrolysis mass spectra. This approach is not limited solely to pyrolysis mass spectrometry but is generally applicable to any analytical tool which is prone to instrumental drift, such as IR, ESR, NMR and other spectroscopies, and gas and liquid chromatography, as well as other types of mass spectrometry.

Ampicillin↗
PubMed2004

Characterization of optically soft spheroidal particles by multiangle light-scattering data by use of the neural-networks method.

A method for evaluating the size of optically soft spheroidal particles by use of the angular structure of scattered light is proposed. It is based on the use of multilevel neural networks with a linear activation function. The retrieval errors of radius R of the equivolume sphere and aspect ratio e are investigated. The ranges of the size of R, e, and the refractive index are 0.3-1.51 microns, 0.2-1, and 1.01-1.02, respectively. The retrieval errors of the equivolume radius and aspect ratio are 0.004 micron and 0.02, respectively, for a three-level neural network (at a precisely measured angular distribution of scattered light). The retrieval errors of R and e for a one-level neural network are 2-5 times greater. The errors for a multilevel neural network increase faster than those for a single-level network.

Journal Article↗
PubMed1992

Inferring articulation and recognizing gestures from acoustics with a neural network trained on x-ray microbeam data.

This paper describes a method for inferring articulatory parameters from acoustics with a neural network trained on paired acoustic and articulatory data. An x-ray microbeam recorded the vertical movements of the lower lip, tongue tip, and tongue dorsum of three speakers saying the English stop consonants in repeated Ce syllables. A neural network was then trained to map from simultaneously recorded acoustic data to the articulatory data. To evaluate learning, acoustics from the training set were passed through the neural network. To evaluate generalization, acoustics from speakers or consonants excluded from the training set were passed through the network. The articulatory trajectories thus inferred were a good fit to the actual movements in both the learning and generalization conditions, as judged by root-mean-square error and correlation. Inferred trajectories were also matched to templates of lower lip, tongue tip, and tongue dorsum release gestures extracted from the original data. This technique correctly recognized from 94.4% to 98.9% of all gestures in the learning and cross-speaker generalization conditions, and 75% of gestures underlying consonants excluded from the training set. In addition, greater regularity was observed for movements of articulators that were critical in the formation of each consonant.

Adult↗
PubMed1998

Predicting outcome of anterior temporal lobectomy using simulated neural networks.

PURPOSE: Anterior temporal lobectomy (ATL) is an important option for treatment of medically refractory seizures. Patient selection is not always clear-cut, and there is inherent morbidity and mortality associated with the invasive and expensive surgical protocols. To determine whether patient selection might be facilitated by application of artificial intelligence, we developed a model that predicted seizure outcome after ATL, using a simulated neural network (SNN). METHODS: Predictions of the model were compared with predictions derived from conventional discriminant function analysis. Neural networks and discriminant functions were devised that would predict the occurrence of both Class 1 outcomes (totally seizure-free), and Class 1 or Class 2 outcomes (nearly or totally seizure-free), using data from 87 patients from three surgical centers. The SNNs and discriminant functions were developed using data from a randomly selected subsample of 65 patients, and both models were cross-validated, using the remaining 22 patients. RESULTS: The discriminant functions showed overall predictive accuracy of 78.5% and 72.7%, while the neural networks demonstrated overall accuracy of 81.8% and 95.4%. CONCLUSIONS: Simulated neural networks show promise as adjuncts to decision-making in the selection of epilepsy surgery patients.

Adolescent↗
PubMed1998

A neural network for the optimization of fed-batch glutamic acid production.

A neural network system, which is composed of a simulation subnetwork and an optimization subnetwork, was constructed to predict and optimize the industrial fed-batch fermentation of glutamic acid. A data-compression and filtration network structure was incorporated into the simulation subnetwork to extract "noise-free" patterns from the input signals. The sole-variant optimization and the multiple-variant optimization can be easily carried out by the neural network developed. A satisfactory result has been achieved.

Computer Simulation↗
PubMed1997

The application of neural networks in predicting the outcome of in-vitro fertilization.

Infertility affects one in six couples at some time in their lives, with 48% of these couples requiring assisted conception techniques in order to achieve a pregnancy. Whilst the overall clinical pregnancy rate per embryo transfer is 23%, this varies widely between clinics. The Human Fertilisation and Embryology Authority has attempted to analyse the results of all units, with weighting of different factors affecting assisted conception, and the published data have invariably led to comparisons between units. However, statistical models need to be developed to eliminate bias for valid comparisons. Neural networks offer a novel approach to pattern recognition. In some instances neural networks can identify a wider range of associations than other statistical techniques due in part to their ability to recognize highly non-linear associations. It was hoped that a neural network approach may be able to predict success for individual couples about to undergo in-vitro fertilization (IVF) treatment. A neural network was constructed using the variables of age, number of eggs recovered, number of embryos transferred and whether there was embryo freezing. Overall the network managed to achieve an accuracy of 59%.

Adult↗
PubMed2004

Content of aliphatic hydrocarbons in limpets as a new way for classification of species using artificial neural networks.

It is demonstrated that biological species like limpets can be classified according to their level of n-alkanes when artificial neural networks are applied. Marine intertidal and subtidal limpets of the Canary Islands (Spain), Patella piperata, Patella candei crenata and Patella ulyssiponensis aspera were selected as bioindicator organisms. Samples were collected at four stations on the coasts of Fuerteventura. Concentration of n-alkanes in the soft tissues of the limpets has been determined by gas chromatography. Data were treated with artificial neural networks (ANNs) and it was found that using suitable architecture of a supervised artificial neural network, the limpets can be successfully distinguished (classified) up to 98%.

Alkanes↗
PubMed2003

Comparison of neural network, Bayesian, and multiple stepwise regression-based limited sampling models to estimate area under the curve.

This study compared limited sampling methods (LSM) of estimating area under the plasma concentration versus time curve (AUC) based on a Bayesian regularized neural network, the Bayesian approach, and multiple forward stepwise regression models from selected concentration-time points. Plasma concentration versus time data sets with a linear two-compartmental pharmacokinetic model were simulated. A limited sampling method based on the forward stepwise regression model was developed and validated. Plasma concentration-time points selected by the stepwise regression model were used for neural network and Bayesian evaluation. In addition, 55 plasma concentration-time profiles from two clinical studies were used to develop and compare the predicted AUC(last) for the three approaches. From simulated data sets, mean prediction errors for AUC(last) estimation were 0.00, -5.32, and -6.06 for the neural network, Bayesian approach, and forward stepwise regression LSM, respectively. Mean square errors were 581, 588, and 618, respectively. For clinical data set, model mean prediction errors were 0.00, 3.51, and 3.87, respectively. Model mean square errors were 30.6, 109, and 76, respectively. For both simulated and clinical data sets, the neural network approach to estimate AUC(last) from selected time points was numerically more precise and significantly less biased than the other two methods.

Antiviral Agents↗